Search

Background: Treatment and preventative advances for chronic obstructive pulmonary disease (COPD) have been slow due, in part, to limited subphenotypes. We tested if unsupervised machine learning on CT images would discover CT emphysema subtypes with distinct characteristics, prognoses and genetic associations., Methods: New CT emphysema subtypes were identified by unsupervised machine learning on only the texture and location of emphysematous regions on CT scans from 2853 participants in the Subpopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS), a COPD case-control study, followed by data reduction. Subtypes were compared with symptoms and physiology among 2949 participants in the population-based Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study and with prognosis among 6658 MESA participants. Associations with genome-wide single-nucleotide-polymorphisms were examined., Results: The algorithm discovered six reproducible (interlearner intraclass correlation coefficient, 0.91-1.00) CT emphysema subtypes. The most common subtype in SPIROMICS, the combined bronchitis-apical subtype, was associated with chronic bronchitis, accelerated lung function decline, hospitalisations, deaths, incident airflow limitation and a gene variant near DRD1 , which is implicated in mucin hypersecretion (p=1.1 ×10 -8 ). The second, the diffuse subtype was associated with lower weight, respiratory hospitalisations and deaths, and incident airflow limitation. The third was associated with age only. The fourth and fifth visually resembled combined pulmonary fibrosis emphysema and had distinct symptoms, physiology, prognosis and genetic associations. The sixth visually resembled vanishing lung syndrome., Conclusion: Large-scale unsupervised machine learning on CT scans defined six reproducible, familiar CT emphysema subtypes that suggest paths to specific diagnosis and personalised therapies in COPD and pre-COPD., Competing Interests: Competing interests: EDA, PPB, AM, YS, WS, JHMA, MHC, DC, EH, DRJ, SK, JDK, TL, JL, ECO, WP, MRP, SSR, EKS, KEW and AFL reports receiving grants from the National Institutes of Health (NIH). JY performed the work at Columbia University but is now an employee of Google. EAH reports receiving grants from the NIH; being a founder and shareholder of VIDA Diagnostics; and holding patents for an apparatus for analysing CT images to determine the presence of pulmonary tissue pathology, an apparatus for image display and analysis, and a method for multiscale meshing of branching biological structures. EBA reports receiving grants from the American Heart Association and the NIH. CBC reports receiving personal fees from GlaxoSmithKline. MTD reports receiving a grant from the NHLBI and personal fees from AstraZeneca, GlaxoSmithKline, Pulmonx, PneumRx/BTG and Quark. MKH reports consulting for GlaxoSmithKline, AstraZeneca and Boehringer Ingelheim receiving research support from Novartis and Sunovion. NNH reports receiving grants from the NIH, Boehringer Ingelheim, and the COPD Foundation. JDK reports receiving grants from US Environmental Protection Agency and the NIH. FJM reports serving on COPD advisory boards for AstraZeneca, Boehringer Ingelheim, Chiesi, GlaxoSmithKline, Sunovion and Teva; serving as a consultant for ProterixBio and Verona; serving on the steering committees of studies sponsored by the NHLBI, AstraZeneca, and GlaxoSmithKline; having served on data safety and monitoring boards of COPD studies supported by Genentech and GlaxoSmithKline. BMS reports receiving grants from the NIH, Canadian Institutes of Health Research (CIHR), Fonds de la recherche en santé du Québec (FRQS), the Research Institute of the McGill University Health Centre, the Quebec Lung Association and AstraZeneca. PGW reports receiving personal fees for consultancy from Theravance, AstraZeneca, Regeneron, Sanofi, Genentech, Roche and Janssen. RGB reports receiving grants from the COPD Foundation, the US Environmental Protection Agency (EPA), the American Lung Association and the NIH., (© Author(s) (or their employer(s)) 2023. No commercial re-use. See rights and permissions. Published by BMJ.)

Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy. Unsupervised learning of emphysema subtypes on computed tomography (CT) opens the way to new definitions of emphysema subtypes and eliminates the need of thorough manual labeling. However, CT-based emphysema subtypes have been limited to texture-based patterns without considering spatial location. In this work, we introduce a standardized spatial mapping of the lung for quantitative study of lung texture location and propose a novel framework for combining spatial and texture information to discover spatially-informed lung texture patterns (sLTPs) that represent novel emphysema subtype candidates. Exploiting two cohorts of full-lung CT scans from the MESA COPD (n = 317) and EMCAP (n = 22) studies, we first show that our spatial mapping enables population-wide study of emphysema spatial location. We then evaluate the characteristics of the sLTPs discovered on MESA COPD, and show that they are reproducible, able to encode standard emphysema subtypes, and associated with physiological symptoms.